Capital One Services, LLC

John Stocker

Sunny Kumar

Alan Rozet

Mark Roberts

Naga V Gumpina

Luke Botti

Diana Yoo

Scott Jemielity

Parth Shrotri

Daniel Snipes

Systems and methods of the present disclosure include at least one processor that receives a data set of a data stream from a data source, where the data set includes a time-varying data points. The processor determines event observations associated with data points of the time-varying data points based on a detection model to identify types of the event observations, including: i) anomalies, ii) change-points, iii) patterns, or iv) outliers. The processor generates anomaly records in an event data store based on the event observations and automatically generates event records for at least one of the anomaly records based on variables of at least one dimension of the time-varying data points, where the event record links one or more event observations. The processor automatically applies changes in the event record to each event observation of the one or more event observations based on the linking by the event record.

Computer-based systems configured for detecting, classifying, and visualizing events in large-scale, multivariate and multidimensional datasets and methods of use thereof

Systems and methods are provided for parallel processing of datasets with dynamic skew compensation. The disclosed systems and methods may increase the efficiency of dataset processing by imposing maximum size limits on parallel processing environment tasks. The disclosed systems and methods may generate a target partition of a variable, a database storing data elements, a cluster that generates one or more output files based on the target partition and the data elements, and a display device that displays analysis results for the target partition using the one or more output files. Generation may comprise creating a calculation partition, mapping data elements according to the calculation partition, and generating the one or more output files based on the mapped data elements. The calculation partition may depend on a target partition and a uniform partition that partitions values based on one or more of statistical measures and pseudorandom functions.

Systems for parallel processing of datasets with dynamic skew compensation

Growing community of inventors

Alexandria, VA, United States of America

John Stocker